Initial commit: Natural Memory Agent Lab：模型服务 + TypeScript agent + 记忆能力场景评测（冲突更新、跨会话回忆、遗忘撤回、多跳、未知拒答）

2026-09-19 12:09:13 +08:00
commit eb9bd87a4d
108 changed files with 6452 additions and 0 deletions
@@ -0,0 +1,23 @@
+{
+  "id": "multi_hop_chain",
+  "description": "两条事实构成推理链（项目→负责人→工号）。跨会话问最终属性时，模型必须串起两跳而不是只取一跳。",
+  "sessions": [
+    {
+      "id": "s1",
+      "turns": [
+        "记两件事：项目 项目-星尘 的负责人是 成员-林澈。",
+        "另外：成员 成员-林澈 的工号是 H-9F3K2。"
+      ]
+    },
+    {
+      "id": "s2",
+      "turns": [
+        "项目-星尘 的负责人的工号是什么？需要的话可以分步推导，最后只回答工号。"
+      ]
+    }
+  ],
+  "assertions": [
+    { "type": "answer_contains", "session": "s2", "turn": 0, "any": ["H-9F3K2", "H 9F3K2", "9F3K2"] },
+    { "type": "answer_not_contains", "session": "s2", "turn": 0, "any": ["不知道", "没有记录"] }
+  ]
+}